© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4517
    Prev
    Next
    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perpetuity
    -0.63
     everlasting
    -0.61
     Always
    -0.60
     Siempre
    -0.60
     perpetual
    -0.57
    Always
    -0.56
     endless
    -0.54
     ALWAYS
    -0.54
     constancy
    -0.53
     Nunca
    -0.52
    POSITIVE LOGITS
    GEBURTSDATUM
    0.93
    ValueStyle
    0.80
    IUrlHelper
    0.69
     kasarigan
    0.67
    はじめに
    0.65
     TODAY
    0.63
    "]]
    0.63
    )]
    
    0.61
     estimés
    0.60
    databind
    0.58
    Activations Density 0.012%

    No Known Activations